feat(recommendation): fall back to liked entities when You-might-like is thin (#790)
test-go / test (push) Failing after 14s
test-go / integration (push) Has been cancelled

The taste roll-up surfaces top-similar albums/artists, which for a heavy
listener are mostly ones they already play — so the read-time dedup (vs Most
Played + Rediscover + Last Played) can strip the section down to a single tile
(reported on the artists row). The code was sound; the section was just starved.

Adds a read-time fallback: when a You-might-like row comes up short after dedup,
top it up from the user's LIKED artists/albums — a far larger pool than the
12-entity similarity roll-up, so the same exclusions still leave plenty. Reuses
the existing Rediscover-fallback queries (no new SQL), applies the same
exclusions (already-shown + Rediscover + Most/Last Played) so it never
duplicates a tile or suggests an actively-played entity, and is best-effort
(a query error leaves the section as-is). Takes effect immediately — no rebuild.

A cold-start user with no likes gets nothing from the fallback, so the
new-user-empty behaviour is preserved (test still passes).

Test: 20 liked artists, none played → Rediscover fills 10, You-might-like
fallback fills the other 10, disjoint.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-11 23:24:21 -04:00
parent 3f240bc777
commit 36786defd1
2 changed files with 126 additions and 0 deletions
+88
View File
@@ -180,9 +180,97 @@ func HomeData(ctx context.Context, pool *pgxpool.Pool, userID pgtype.UUID) (*Hom
out.YouMightLikeAlbums, out.MostPlayedTracks, out.RediscoverAlbums)
out.YouMightLikeArtists = applyYouMightLikeArtistFilters(
out.YouMightLikeArtists, out.MostPlayedTracks, out.RediscoverArtists, out.LastPlayedArtists)
// The taste roll-up surfaces top-similar entities, which for a heavy
// listener are mostly ones they already play — so the dedup above can
// leave the section thin (often a single artist). Top up from the much
// larger pool of liked entities, applying the same exclusions so the
// fallback neither duplicates a tile nor suggests an actively-played one.
if len(out.YouMightLikeArtists) < HomeYouMightLikeLimit {
out.YouMightLikeArtists = topUpYouMightLikeArtists(ctx, q, userID, out)
}
if len(out.YouMightLikeAlbums) < HomeYouMightLikeLimit {
out.YouMightLikeAlbums = topUpYouMightLikeAlbums(ctx, q, userID, out)
}
return out, nil
}
// youMightLikeFallbackFetch is the liked-entity pool the fallback draws from.
// Generous so the dedup still leaves enough to fill the row.
const youMightLikeFallbackFetch = 100
// topUpYouMightLikeArtists fills a thin You-might-like artist row from the
// user's liked artists (daily-stable sample), excluding what's already shown
// on Home (the section itself, Rediscover, Most/Last Played) so the fallback
// neither duplicates a tile nor suggests an actively-played artist. The liked
// pool dwarfs the similarity roll-up, so the same exclusions still fill it.
// Best-effort: a query error leaves the section as-is.
func topUpYouMightLikeArtists(
ctx context.Context, q *dbq.Queries, userID pgtype.UUID, out *HomePayload,
) []dbq.ListYouMightLikeArtistsForUserRow {
excluded := mostPlayedArtistIDs(out.MostPlayedTracks)
for _, r := range out.RediscoverArtists {
excluded[r.Artist.ID] = struct{}{}
}
for _, r := range out.LastPlayedArtists {
excluded[r.Artist.ID] = struct{}{}
}
result := out.YouMightLikeArtists
for _, r := range result {
excluded[r.Artist.ID] = struct{}{}
}
fb, err := q.ListRediscoverArtistsFallbackForUser(ctx, dbq.ListRediscoverArtistsFallbackForUserParams{
UserID: userID, Limit: youMightLikeFallbackFetch,
})
if err != nil {
return result
}
for _, r := range fb {
if _, dup := excluded[r.Artist.ID]; dup {
continue
}
result = append(result, dbq.ListYouMightLikeArtistsForUserRow{
Artist: r.Artist, CoverAlbumID: r.CoverAlbumID, AlbumCount: r.AlbumCount,
})
if len(result) >= HomeYouMightLikeLimit {
break
}
}
return result
}
// topUpYouMightLikeAlbums is the album-row counterpart to
// topUpYouMightLikeArtists, drawing from the user's liked albums.
func topUpYouMightLikeAlbums(
ctx context.Context, q *dbq.Queries, userID pgtype.UUID, out *HomePayload,
) []dbq.ListYouMightLikeAlbumsForUserRow {
excluded := mostPlayedAlbumIDs(out.MostPlayedTracks)
for _, r := range out.RediscoverAlbums {
excluded[r.Album.ID] = struct{}{}
}
result := out.YouMightLikeAlbums
for _, r := range result {
excluded[r.Album.ID] = struct{}{}
}
fb, err := q.ListRediscoverAlbumsFallbackForUser(ctx, dbq.ListRediscoverAlbumsFallbackForUserParams{
UserID: userID, Limit: youMightLikeFallbackFetch,
})
if err != nil {
return result
}
for _, r := range fb {
if _, dup := excluded[r.Album.ID]; dup {
continue
}
result = append(result, dbq.ListYouMightLikeAlbumsForUserRow{
Album: r.Album, ArtistName: r.ArtistName,
})
if len(result) >= HomeYouMightLikeLimit {
break
}
}
return result
}
// applyYouMightLikeAlbumFilters drops albums the user actively plays
// (Most Played) or that already appear in Rediscover, then trims to
// HomeYouMightLikeLimit. Build-time rank order is preserved.
@@ -2,6 +2,7 @@ package recommendation
import (
"context"
"fmt"
"testing"
"time"
@@ -10,6 +11,43 @@ import (
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
)
// TestHomeData_YouMightLike_FallbackFillsFromLikedArtists: when the taste
// roll-up is empty/thin (no you_might_like_artists rows here), the section
// fills from the user's liked artists. Rediscover takes its share first; the
// You-might-like fallback fills the rest disjointly so no artist is shown
// twice. 20 liked artists, none played → Rediscover 10 + You-might-like 10.
func TestHomeData_YouMightLike_FallbackFillsFromLikedArtists(t *testing.T) {
pool := newPool(t)
user := seedUser(t, pool, "home-yml-fallback")
liked := make(map[pgtype.UUID]bool, 20)
for i := 0; i < 20; i++ {
a := seedArtist(t, pool, fmt.Sprintf("YmlArtist%02d", i), "")
likeArtist(t, pool, user.ID, a.ID)
liked[a.ID] = true
}
got, err := HomeData(context.Background(), pool, user.ID)
if err != nil {
t.Fatalf("HomeData: %v", err)
}
if len(got.YouMightLikeArtists) != HomeYouMightLikeLimit {
t.Fatalf("you-might-like artists = %d, want %d (filled by fallback)",
len(got.YouMightLikeArtists), HomeYouMightLikeLimit)
}
inRediscover := map[pgtype.UUID]bool{}
for _, r := range got.RediscoverArtists {
inRediscover[r.Artist.ID] = true
}
for _, r := range got.YouMightLikeArtists {
if !liked[r.Artist.ID] {
t.Errorf("you-might-like artist %s not from the liked pool", r.Artist.Name)
}
if inRediscover[r.Artist.ID] {
t.Errorf("artist %s shown in both Rediscover and You-might-like", r.Artist.Name)
}
}
}
func TestHomeData_NewUser_AllSectionsEmpty(t *testing.T) {
pool := newPool(t)
user := seedUser(t, pool, "home-newuser")